zr-project-setup

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs routine project management tasks using specialized internal tools (probe). No evidence of malicious intent, obfuscation, or security violations was found.
  • [COMMAND_EXECUTION]: The commands defined in SKILL.md utilize a specific CLI tool (probe) to create and update project records. These operations are consistent with the skill's stated purpose and use variables that are expected to be populated from internal 'idea' records.
  • [DATA_EXFILTRATION]: The skill does not access sensitive system files (e.g., SSH keys, AWS credentials) or perform network operations to untrusted domains. Messaging is restricted to an internal 'general' channel via the probe message tool.
  • [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety guidelines, or extract system prompts were detected in the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 02:49 AM